nodmix 2026.5.25

package/docs/tools/kimi-search.md

@@ -0,0 +1,105 @@
+---
+summary: "Kimi web search via Moonshot web search"
+read_when:
+  - You want to use Kimi for web_search
+  - You need a KIMI_API_KEY or MOONSHOT_API_KEY
+title: "Kimi search"
+---
+
+Nodmix supports Kimi as a `web_search` provider, using Moonshot web search
+to produce AI-synthesized answers with citations.
+
+## Get an API key
+
+<Steps>
+  <Step title="Create a key">
+    Get an API key from [Moonshot AI](https://platform.moonshot.cn/).
+  </Step>
+  <Step title="Store the key">
+    Set `KIMI_API_KEY` or `MOONSHOT_API_KEY` in the Gateway environment, or
+    configure via:
+
+    ```bash
+    nodmix configure --section web
+    ```
+
+  </Step>
+</Steps>
+
+When you choose **Kimi** during `nodmix onboard` or
+`nodmix configure --section web`, Nodmix can also ask for:
+
+- the Moonshot API region:
+  - `https://api.moonshot.ai/v1`
+  - `https://api.moonshot.cn/v1`
+- the default Kimi web-search model (defaults to `kimi-k2.6`)
+
+## Config
+
+```json5
+{
+  plugins: {
+    entries: {
+      moonshot: {
+        config: {
+          webSearch: {
+            apiKey: "sk-...", // optional if KIMI_API_KEY or MOONSHOT_API_KEY is set
+            baseUrl: "https://api.moonshot.ai/v1",
+            model: "kimi-k2.6",
+          },
+        },
+      },
+    },
+  },
+  tools: {
+    web: {
+      search: {
+        provider: "kimi",
+      },
+    },
+  },
+}
+```
+
+If you use the China API host for chat (`models.providers.moonshot.baseUrl`:
+`https://api.moonshot.cn/v1`), Nodmix reuses that same host for Kimi
+`web_search` when `tools.web.search.kimi.baseUrl` is omitted, so keys from
+[platform.moonshot.cn](https://platform.moonshot.cn/) do not hit the
+international endpoint by mistake (which often returns HTTP 401). Override
+with `tools.web.search.kimi.baseUrl` when you need a different search base URL.
+
+**Environment alternative:** set `KIMI_API_KEY` or `MOONSHOT_API_KEY` in the
+Gateway environment. For a gateway install, put it in `~/.nodmix/.env`.
+
+If you omit `baseUrl`, Nodmix defaults to `https://api.moonshot.ai/v1`.
+If you omit `model`, Nodmix defaults to `kimi-k2.6`.
+
+## How it works
+
+Kimi uses Moonshot web search to synthesize answers with inline citations,
+similar to Gemini and Grok's grounded response approach.
+
+Nodmix treats Kimi `web_search` as successful only after Moonshot returns
+native web-search grounding evidence, such as a replayable `$web_search` tool
+payload, `search_results`, or citation URLs. If Kimi stops immediately with a
+plain chat answer like "I cannot browse the internet" and no grounding evidence,
+Nodmix returns a structured `kimi_web_search_ungrounded` error instead of
+wrapping that text as a search result. Retry the query, switch to a structured
+provider such as Brave, or use `web_fetch` / the browser tool when you already
+have a target URL.
+
+## Supported parameters
+
+Kimi search supports `query`.
+
+`count` is accepted for shared `web_search` compatibility, but Kimi still
+returns one synthesized answer with citations rather than an N-result list.
+
+Provider-specific filters are not currently supported.
+
+## Related
+
+- [Web Search overview](/tools/web) -- all providers and auto-detection
+- [Moonshot AI](/providers/moonshot) -- Moonshot model + Kimi Coding provider docs
+- [Gemini Search](/tools/gemini-search) -- AI-synthesized answers via Google grounding
+- [Grok Search](/tools/grok-search) -- AI-synthesized answers via xAI grounding

package/docs/tools/llm-task.md

@@ -0,0 +1,137 @@
+---
+summary: "JSON-only LLM tasks for workflows (optional plugin tool)"
+read_when:
+  - You want a JSON-only LLM step inside workflows
+  - You need schema-validated LLM output for automation
+title: "LLM task"
+---
+
+`llm-task` is an **optional plugin tool** that runs a JSON-only LLM task and
+returns structured output (optionally validated against JSON Schema).
+
+This is ideal for workflow engines like Lobster: you can add a single LLM step
+without writing custom Nodmix code for each workflow.
+
+## Enable the plugin
+
+1. Enable the plugin:
+
+```json
+{
+  "plugins": {
+    "entries": {
+      "llm-task": { "enabled": true }
+    }
+  }
+}
+```
+
+2. Allow the optional tool:
+
+```json
+{
+  "tools": {
+    "alsoAllow": ["llm-task"]
+  }
+}
+```
+
+Use `tools.allow` only when you want restrictive allowlist mode.
+
+## Config (optional)
+
+```json
+{
+  "plugins": {
+    "entries": {
+      "llm-task": {
+        "enabled": true,
+        "config": {
+          "defaultProvider": "openai-codex",
+          "defaultModel": "gpt-5.5",
+          "defaultAuthProfileId": "main",
+          "allowedModels": ["openai/gpt-5.4"],
+          "maxTokens": 800,
+          "timeoutMs": 30000
+        }
+      }
+    }
+  }
+}
+```
+
+`allowedModels` is an allowlist of `provider/model` strings. If set, any request
+outside the list is rejected.
+
+## Tool parameters
+
+- `prompt` (string, required)
+- `input` (any, optional)
+- `schema` (object, optional JSON Schema)
+- `provider` (string, optional)
+- `model` (string, optional)
+- `thinking` (string, optional)
+- `authProfileId` (string, optional)
+- `temperature` (number, optional)
+- `maxTokens` (number, optional)
+- `timeoutMs` (number, optional)
+
+`thinking` accepts the standard Nodmix reasoning presets, such as `low` or `medium`.
+
+## Output
+
+Returns `details.json` containing the parsed JSON (and validates against
+`schema` when provided).
+
+## Example: Lobster workflow step
+
+### Important limitation
+
+The example below assumes the **standalone Lobster CLI** is running in an environment where `nodmix.invoke` already has the correct gateway URL/auth context.
+
+For the bundled **embedded** Lobster runner inside Nodmix, this nested CLI pattern is **not currently reliable**:
+
+```lobster
+nodmix.invoke --tool llm-task --action json --args-json '{ ... }'
+```
+
+Until embedded Lobster has a supported bridge for this flow, prefer either:
+
+- direct `llm-task` tool calls outside Lobster, or
+- Lobster steps that do not rely on nested `nodmix.invoke` calls.
+
+Standalone Lobster CLI example:
+
+```lobster
+nodmix.invoke --tool llm-task --action json --args-json '{
+  "prompt": "Given the input email, return intent and draft.",
+  "thinking": "low",
+  "input": {
+    "subject": "Hello",
+    "body": "Can you help?"
+  },
+  "schema": {
+    "type": "object",
+    "properties": {
+      "intent": { "type": "string" },
+      "draft": { "type": "string" }
+    },
+    "required": ["intent", "draft"],
+    "additionalProperties": false
+  }
+}'
+```
+
+## Safety notes
+
+- The tool is **JSON-only** and instructs the model to output only JSON (no
+  code fences, no commentary).
+- No tools are exposed to the model for this run.
+- Treat output as untrusted unless you validate with `schema`.
+- Put approvals before any side-effecting step (send, post, exec).
+
+## Related
+
+- [Thinking levels](/tools/thinking)
+- [Sub-agents](/tools/subagents)
+- [Slash commands](/tools/slash-commands)

package/docs/tools/lobster.md

@@ -0,0 +1,365 @@
+---
+summary: "Typed workflow runtime for Nodmix with resumable approval gates."
+title: Lobster
+read_when:
+  - You want deterministic multi-step workflows with explicit approvals
+  - You need to resume a workflow without re-running earlier steps
+---
+
+Lobster is a workflow shell that lets Nodmix run multi-step tool sequences as a single, deterministic operation with explicit approval checkpoints.
+
+Lobster is one authoring layer above detached background work. For flow orchestration above individual tasks, see [Task Flow](/automation/taskflow) (`nodmix tasks flow`). For the task activity ledger, see [`nodmix tasks`](/automation/tasks).
+
+## Hook
+
+Your assistant can build the tools that manage itself. Ask for a workflow, and 30 minutes later you have a CLI plus pipelines that run as one call. Lobster is the missing piece: deterministic pipelines, explicit approvals, and resumable state.
+
+## Why
+
+Today, complex workflows require many back-and-forth tool calls. Each call costs tokens, and the LLM has to orchestrate every step. Lobster moves that orchestration into a typed runtime:
+
+- **One call instead of many**: Nodmix runs one Lobster tool call and gets a structured result.
+- **Approvals built in**: Side effects (send email, post comment) halt the workflow until explicitly approved.
+- **Resumable**: Halted workflows return a token; approve and resume without re-running everything.
+
+## Why a DSL instead of plain programs?
+
+Lobster is intentionally small. The goal is not "a new language," it's a predictable, AI-friendly pipeline spec with first-class approvals and resume tokens.
+
+- **Approve/resume is built in**: A normal program can prompt a human, but it can't _pause and resume_ with a durable token without you inventing that runtime yourself.
+- **Determinism + auditability**: Pipelines are data, so they're easy to log, diff, replay, and review.
+- **Constrained surface for AI**: A tiny grammar + JSON piping reduces "creative" code paths and makes validation realistic.
+- **Safety policy baked in**: Timeouts, output caps, sandbox checks, and allowlists are enforced by the runtime, not each script.
+- **Still programmable**: Each step can call any CLI or script. If you want JS/TS, generate `.lobster` files from code.
+
+## How it works
+
+Nodmix runs Lobster workflows **in-process** using an embedded runner. No external CLI subprocess is spawned; the workflow engine executes inside the gateway process and returns a JSON envelope directly.
+If the pipeline pauses for approval, the tool returns a `resumeToken` so you can continue later.
+
+## Pattern: small CLI + JSON pipes + approvals
+
+Build tiny commands that speak JSON, then chain them into a single Lobster call. (Example command names below - swap in your own.)
+
+```bash
+inbox list --json
+inbox categorize --json
+inbox apply --json
+```
+
+```json
+{
+  "action": "run",
+  "pipeline": "exec --json --shell 'inbox list --json' | exec --stdin json --shell 'inbox categorize --json' | exec --stdin json --shell 'inbox apply --json' | approve --preview-from-stdin --limit 5 --prompt 'Apply changes?'",
+  "timeoutMs": 30000
+}
+```
+
+If the pipeline requests approval, resume with the token:
+
+```json
+{
+  "action": "resume",
+  "token": "<resumeToken>",
+  "approve": true
+}
+```
+
+AI triggers the workflow; Lobster executes the steps. Approval gates keep side effects explicit and auditable.
+
+Example: map input items into tool calls:
+
+```bash
+gog.gmail.search --query 'newer_than:1d' \
+  | nodmix.invoke --tool message --action send --each --item-key message --args-json '{"provider":"telegram","to":"..."}'
+```
+
+## JSON-only LLM steps (llm-task)
+
+For workflows that need a **structured LLM step**, enable the optional
+`llm-task` plugin tool and call it from Lobster. This keeps the workflow
+deterministic while still letting you classify/summarize/draft with a model.
+
+Enable the tool:
+
+```json
+{
+  "plugins": {
+    "entries": {
+      "llm-task": { "enabled": true }
+    }
+  },
+  "agents": {
+    "list": [
+      {
+        "id": "main",
+        "tools": { "alsoAllow": ["llm-task"] }
+      }
+    ]
+  }
+}
+```
+
+### Important limitation: embedded Lobster vs `nodmix.invoke`
+
+The bundled Lobster plugin runs workflows **in-process** inside the gateway. In that embedded mode, `nodmix.invoke` does **not** automatically inherit a gateway URL/auth context for nested Nodmix CLI tool calls.
+
+That means this pattern is **not currently reliable in the embedded runner**:
+
+```lobster
+nodmix.invoke --tool llm-task --action json --args-json '{ ... }'
+```
+
+Use the example below only when running the **standalone Lobster CLI** in an environment where `nodmix.invoke` is already configured with the correct gateway/auth context.
+
+Use it in a standalone Lobster CLI pipeline:
+
+```lobster
+nodmix.invoke --tool llm-task --action json --args-json '{
+  "prompt": "Given the input email, return intent and draft.",
+  "thinking": "low",
+  "input": { "subject": "Hello", "body": "Can you help?" },
+  "schema": {
+    "type": "object",
+    "properties": {
+      "intent": { "type": "string" },
+      "draft": { "type": "string" }
+    },
+    "required": ["intent", "draft"],
+    "additionalProperties": false
+  }
+}'
+```
+
+If you are using the embedded Lobster plugin today, prefer either:
+
+- a direct `llm-task` tool call outside Lobster, or
+- non-`nodmix.invoke` steps inside the Lobster pipeline until a supported embedded bridge is added.
+
+See [LLM Task](/tools/llm-task) for details and configuration options.
+
+## Workflow files (.lobster)
+
+Lobster can run YAML/JSON workflow files with `name`, `args`, `steps`, `env`, `condition`, and `approval` fields. In Nodmix tool calls, set `pipeline` to the file path.
+
+```yaml
+name: inbox-triage
+args:
+  tag:
+    default: "family"
+steps:
+  - id: collect
+    command: inbox list --json
+  - id: categorize
+    command: inbox categorize --json
+    stdin: $collect.stdout
+  - id: approve
+    command: inbox apply --approve
+    stdin: $categorize.stdout
+    approval: required
+  - id: execute
+    command: inbox apply --execute
+    stdin: $categorize.stdout
+    condition: $approve.approved
+```
+
+Notes:
+
+- `stdin: $step.stdout` and `stdin: $step.json` pass a prior step's output.
+- `condition` (or `when`) can gate steps on `$step.approved`.
+
+## Install Lobster
+
+Bundled Lobster workflows run in-process; no separate `lobster` binary is required. The embedded runner ships with the Lobster plugin.
+
+If you need the standalone Lobster CLI for development or external pipelines, install it from the [Lobster repo](https://github.com/nodmix/lobster) and ensure `lobster` is on `PATH`.
+
+## Enable the tool
+
+Lobster is an **optional** plugin tool (not enabled by default).
+
+Recommended (additive, safe):
+
+```json
+{
+  "tools": {
+    "alsoAllow": ["lobster"]
+  }
+}
+```
+
+Or per-agent:
+
+```json
+{
+  "agents": {
+    "list": [
+      {
+        "id": "main",
+        "tools": {
+          "alsoAllow": ["lobster"]
+        }
+      }
+    ]
+  }
+}
+```
+
+Avoid using `tools.allow: ["lobster"]` unless you intend to run in restrictive allowlist mode.
+
+<Note>
+Allowlists are opt-in for optional plugins. `alsoAllow` enables only the named optional plugin tools while preserving the normal core tool set. To restrict core tools, use `tools.allow` with the core tools or groups you want.
+</Note>
+
+## Example: Email triage
+
+Without Lobster:
+
+```
+User: "Check my email and draft replies"
+→ nodmix calls gmail.list
+→ LLM summarizes
+→ User: "draft replies to #2 and #5"
+→ LLM drafts
+→ User: "send #2"
+→ nodmix calls gmail.send
+(repeat daily, no memory of what was triaged)
+```
+
+With Lobster:
+
+```json
+{
+  "action": "run",
+  "pipeline": "email.triage --limit 20",
+  "timeoutMs": 30000
+}
+```
+
+Returns a JSON envelope (truncated):
+
+```json
+{
+  "ok": true,
+  "status": "needs_approval",
+  "output": [{ "summary": "5 need replies, 2 need action" }],
+  "requiresApproval": {
+    "type": "approval_request",
+    "prompt": "Send 2 draft replies?",
+    "items": [],
+    "resumeToken": "..."
+  }
+}
+```
+
+User approves → resume:
+
+```json
+{
+  "action": "resume",
+  "token": "<resumeToken>",
+  "approve": true
+}
+```
+
+One workflow. Deterministic. Safe.
+
+## Tool parameters
+
+### `run`
+
+Run a pipeline in tool mode.
+
+```json
+{
+  "action": "run",
+  "pipeline": "gog.gmail.search --query 'newer_than:1d' | email.triage",
+  "cwd": "workspace",
+  "timeoutMs": 30000,
+  "maxStdoutBytes": 512000
+}
+```
+
+Run a workflow file with args:
+
+```json
+{
+  "action": "run",
+  "pipeline": "/path/to/inbox-triage.lobster",
+  "argsJson": "{\"tag\":\"family\"}"
+}
+```
+
+### `resume`
+
+Continue a halted workflow after approval.
+
+```json
+{
+  "action": "resume",
+  "token": "<resumeToken>",
+  "approve": true
+}
+```
+
+### Optional inputs
+
+- `cwd`: Relative working directory for the pipeline (must stay within the gateway working directory).
+- `timeoutMs`: Abort the workflow if it exceeds this duration (default: 20000).
+- `maxStdoutBytes`: Abort the workflow if output exceeds this size (default: 512000).
+- `argsJson`: JSON string passed to `lobster run --args-json` (workflow files only).
+
+## Output envelope
+
+Lobster returns a JSON envelope with one of three statuses:
+
+- `ok` → finished successfully
+- `needs_approval` → paused; `requiresApproval.resumeToken` is required to resume
+- `cancelled` → explicitly denied or cancelled
+
+The tool surfaces the envelope in both `content` (pretty JSON) and `details` (raw object).
+
+## Approvals
+
+If `requiresApproval` is present, inspect the prompt and decide:
+
+- `approve: true` → resume and continue side effects
+- `approve: false` → cancel and finalize the workflow
+
+Use `approve --preview-from-stdin --limit N` to attach a JSON preview to approval requests without custom jq/heredoc glue. Resume tokens are now compact: Lobster stores workflow resume state under its state dir and hands back a small token key.
+
+## OpenProse
+
+OpenProse pairs well with Lobster: use `/prose` to orchestrate multi-agent prep, then run a Lobster pipeline for deterministic approvals. If a Prose program needs Lobster, allow the `lobster` tool for sub-agents via `tools.subagents.tools`. See [OpenProse](/prose).
+
+## Safety
+
+- **Local in-process only** - workflows execute inside the gateway process; no network calls from the plugin itself.
+- **No secrets** - Lobster doesn't manage OAuth; it calls Nodmix tools that do.
+- **Sandbox-aware** - disabled when the tool context is sandboxed.
+- **Hardened** - timeouts and output caps enforced by the embedded runner.
+
+## Troubleshooting
+
+- **`lobster timed out`** → increase `timeoutMs`, or split a long pipeline.
+- **`lobster output exceeded maxStdoutBytes`** → raise `maxStdoutBytes` or reduce output size.
+- **`lobster returned invalid JSON`** → ensure the pipeline runs in tool mode and prints only JSON.
+- **`lobster failed`** → check gateway logs for the embedded runner error details.
+
+## Learn more
+
+- [Plugins](/tools/plugin)
+- [Plugin tool authoring](/plugins/building-plugins#registering-agent-tools)
+
+## Case study: community workflows
+
+One public example: a "second brain" CLI + Lobster pipelines that manage three Markdown vaults (personal, partner, shared). The CLI emits JSON for stats, inbox listings, and stale scans; Lobster chains those commands into workflows like `weekly-review`, `inbox-triage`, `memory-consolidation`, and `shared-task-sync`, each with approval gates. AI handles judgment (categorization) when available and falls back to deterministic rules when not.
+
+- Thread: [https://x.com/plattenschieber/status/2014508656335770033](https://x.com/plattenschieber/status/2014508656335770033)
+- Repo: [https://github.com/bloomedai/brain-cli](https://github.com/bloomedai/brain-cli)
+
+## Related
+
+- [Automation](/automation) - scheduling Lobster workflows
+- [Automation Overview](/automation) - all automation mechanisms
+- [Tools Overview](/tools) - all available agent tools